Deep learning generalizes because the parameter-function map is biased towards simple functions

22 May 2018

Papers citing "Deep learning generalizes because the parameter-function map is biased towards simple functions"

4 / 54 papers shown

Title
Do Deep Nets Really Need to be Deep? Lei Jimmy Ba R. Caruana 151 2,114 0 21 Dec 2013
Improving neural networks by preventing co-adaptation of feature detectors Geoffrey E. Hinton Nitish Srivastava A. Krizhevsky Ilya Sutskever Ruslan Salakhutdinov VLM 387 7,650 0 03 Jul 2012
No Free Lunch versus Occam's Razor in Supervised Learning Tor Lattimore Marcus Hutter UQCV FedML 55 44 0 16 Nov 2011
Robustness and Generalization Huan Xu Shie Mannor OOD 162 459 0 13 May 2010